claude-code-proxy vs otari
LLM provider proxies and gateways compared
claude-code-proxy translates Anthropic-format requests so clients such as Claude Code can use OpenAI, Gemini, or Anthropic backends. otari provides a self-hosted, shared API gateway with provider routing, access controls, budgets, and usage tracking for teams.
claude-code-proxy: Connect Claude Code to Other Model Providers
A Python proxy that lets Anthropic-compatible clients such as Claude Code use OpenAI, Gemini, or Anthropic backends through LiteLLM. It suits developers who want to route Claude-style requests to another provider.
otari: Run an OpenAI-Compatible LLM Gateway
Otari is Mozilla AI’s self-hostable LLM gateway, using any-llm to route OpenAI- and Anthropic-compatible requests to providers through one endpoint. It adds virtual keys, budgets, routing policies, and usage tracking for teams operating their own AI stack.
| claude-code-proxy | otari | |
|---|---|---|
| Language | Python | Python |
| License | — | Apache-2.0 |
| Stars | 3.8k | 660 |
| Forks | 494 | 83 |
| Last analyzed | Oct 9, 2026 | Oct 19, 2026 |
Key differences
- claude-code-proxy focuses on translating Anthropic-compatible client requests, while otari provides both OpenAI- and Anthropic-compatible endpoints.
- claude-code-proxy routes to OpenAI, Gemini, or Anthropic; otari integrates with more than 40 providers through any-llm.
- claude-code-proxy maps Claude-style model requests to configurable provider models, while otari offers policies for failover, weighting, and learned selection.
- otari includes virtual keys, budget checks, usage records, and a dashboard; claude-code-proxy focuses on request translation and provider selection.
- Both are written in Python, but otari specifies Python 3.13 or later for development and has an Apache-2.0 license.
- claude-code-proxy can run from source with uv or in Docker; otari can run standalone with its own database or connect a data plane to otari.ai.
Choose claude-code-proxy if you…
- want to keep using an Anthropic-compatible client such as Claude Code with OpenAI or Gemini models.
- need configurable mappings from Claude-style model requests to OpenAI or Google models.
- want a proxy that can also route directly to Anthropic and handle streaming or non-streaming responses.
Choose otari if you…
- need a shared OpenAI- and Anthropic-compatible endpoint across many providers.
- want scoped virtual keys, budget checks, and usage records for teams.
- need routing policies or a dashboard, and are prepared to operate a self-hosted gateway and database.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.